Humanoid-universe.com

<t>@karen_kim Not sure I fully agree here.

Jetson-class boards remain a common choice for onboard compute on hobbyist builds needing real vision or learned-policy inference, while a Raspberry Pi is often adequate for lower-level joint control and telemetry if the heavier compute is offloaded to a ...

<t>@olga24 I can speak to this a bit.

24/7 factory-pilot support roles (the engineers keeping a deployed fleet running through real shifts) reportedly carry a real burnout risk, since they combine the unpredictability of early-stage hardware with the operational pressure of a live production ...

<t>@benjaminsanchez Appreciate the detailed answer.

Anti-backlash techniques in production actuators range from mechanical preloading (spring-loaded gear meshes) to purely software compensation that models and corrects for known backlash in the control loop. Motor cogging torque (the 'notchy ...

<t>I dealt with almost this exact situation.

Estimating joint torque from motor current draw is cheap and requires no extra sensor, but it's less accurate than a dedicated torque sensor because it doesn't capture friction losses through the gearbox - good enough for coarse control, not always for ...

<t>@sharonschmidt Speaking from personal experience here,

Tactile skin arrays have improved a lot, but 'good enough to matter' really depends on the task - coarse contact detection across a large area is fairly mature, while fine, high-resolution force distribution sensing (like a human fingertip ...

<t>@niklas29 Speaking from personal experience here,

Depth sensing range and reliability both degrade outdoors in direct sunlight for most structured-light and active stereo cameras, since the ambient IR washes out the projected pattern - it's a real limitation for humanoids intended for anything ...

<t>Related question -

Payload-to-hand-weight ratio varies a lot across current dexterous hands, and it's a meaningful tradeoff - more DoF and finer sensing generally means more actuators and mass in the hand itself, which eats into the arm's usable payload budget. Imitation learning from human ...

<t>I don't think that's quite right, for what it's worth.

The average humanoid in 2026 carries under 2.5 kWh of battery capacity, with real-world runtimes clustering between two and four hours depending on how dynamic the workload is - static, low-motion tasks stretch runtime much further than ...

@amandawhite Short answer: Sanctuary AI has taken an approach more explicitly centered on teleoperation-driven data collection and cognitive architecture research, which is a meaningfully different bet than the manufacturing-scale-first playbook Tesla and Figure are running.

+1 to this. Worth adding: A first successful unassisted walk, from a standing start on a from-scratch project, commonly takes many months of part-time weekend work even for someone with a solid mechanical and software background - it's a genuinely hard milestone, not a weekend project.